How can I use Scikit-learn for outlier detection?

How can I use Scikit-learn for outlier detection?

You can use Scikit-learn's Isolation Forest or Local Outlier Factor for outlier detection. Would you like a code example?

Yes, please provide a code example for Isolation Forest.

Sure! Here's a simple example:

from sklearn.ensemble import IsolationForest
import numpy as np

# Sample data
X = np.array([[1], [2], [3], [4], [100]])

# Create the model
model = IsolationForest()
model.fit(X)

# Predict outliers
outliers = model.predict(X)
print(outliers)  # -1 for outliers, 1 for inliers

What do the output values -1 and 1 mean?

In the output, -1 indicates an outlier, while 1 indicates an inlier. So, in your example, the value 100 would be flagged as an outlier.